{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T05:23:25Z","timestamp":1747977805042,"version":"3.28.0"},"reference-count":102,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191736","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-10","source":"Crossref","is-referenced-by-count":4,"title":["Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study"],"prefix":"10.1109","author":[{"given":"Muzhou","family":"Yu","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University"}]},{"given":"Linfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Kaisheng","family":"Ma","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00339"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"ref59","article-title":"Learning sparse neural networks through 1_0 regularization","author":"louizos","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref58","article-title":"Rethinking the value of network pruning","author":"liu","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00668"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_39"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01200"},{"key":"ref54","article-title":"Weight distillation: Transferring the knowledge in neural network parameters","author":"lin","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref51","article-title":"Dada: differentiable automatic data augmentation","author":"li","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_2"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00040"},{"key":"ref45","first-page":"598","article-title":"Optimal brain damage","author":"yann","year":"1990","journal-title":"Advances in neural information processing systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.776"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00533"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5866"},{"key":"ref41","article-title":"Benchmarking the robustness of semantic segmentation models","volume":"abs 1908 5005","author":"kamann","year":"2019","journal-title":"ArXiv"},{"key":"ref44","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NeurIPS"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2072"},{"key":"ref49","article-title":"Revisiting discriminator in GAN compression: A generator- discriminator cooperative compression scheme","volume":"abs 2110 14439","author":"li","year":"2021","journal-title":"CoRR"},{"key":"ref8","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Chasing sparsity in vision transformers: An end-to- end exploration","volume":"34","author":"chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Multi-task pruning for semantic segmentation networks","author":"chen","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref3","article-title":"Anchor pruning for object detection","author":"bonnaerens","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00154"},{"key":"ref5","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","author":"chen","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref101","article-title":"Incremental network quantization: Towards lossless cnns with low- precision weights","author":"zhou","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01339"},{"key":"ref35","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"CVPR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref37","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and i 0.5 mb model size","author":"iandola","year":"2016","journal-title":"ICLRE"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref33","first-page":"2731","article-title":"Population based augmentation: Efficient learning of augmentation policy schedules","author":"ho","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref32","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2014","journal-title":"NeurIPS"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00394"},{"key":"ref38","first-page":"10","article-title":"Style augmentation: data augmentation via style randomization","volume":"6","author":"jackson","year":"0","journal-title":"CVPR Workshops"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00100"},{"key":"ref20","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2016","journal-title":"ICLRE"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_1"},{"key":"ref21","first-page":"164","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","author":"hassibi","year":"1993","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref29","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume":"abs 1903 12261","author":"hendrycks","year":"2019","journal-title":"ArXiv"},{"key":"ref13","article-title":"An empirical analysis of the impact of data augmentation on knowledge distillation","author":"das","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref12","article-title":"Autoaugment: Learning augmentation policies from data","volume":"abs 1805 9501","author":"cubuk","year":"2018","journal-title":"ArXiv"},{"key":"ref15","article-title":"Improved regularization of convolutional neural networks with cutout","author":"devries","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"NAACL"},{"journal-title":"Be your own teacher Improve the performance of convolutional neural networks via self distillation","year":"2019","author":"zhang","key":"ref97"},{"key":"ref96","article-title":"Task-oriented feature distillation","author":"zhang","year":"2020","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00045"},{"key":"ref10","article-title":"Pact: Parameterized clipping activation for quantized neural networks","author":"choi","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref98","article-title":"Scan: A scalable neural networks framework towards compact and efficient models","volume":"abs 1906 3951","author":"zhang","year":"2019","journal-title":"ArXiv"},{"key":"ref17","article-title":"Role-wise data augmentation for knowledge distillation","author":"fu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803505"},{"key":"ref18","article-title":"Role-wise data augmentation for knowledge distillation","author":"fu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref93","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref92","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"2017","journal-title":"ICLRE"},{"key":"ref95","article-title":"Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors","author":"zhang","year":"2021","journal-title":"ICLRE"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01214"},{"key":"ref91","article-title":"Slimmable neural networks","author":"yu","year":"2019","journal-title":"ICLRE"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00840"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.633"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.03.056"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00020"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCT46805.2019.8947189"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1670"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00507"},{"key":"ref84","article-title":"Lite transformer with long-short range attention","author":"wu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_36"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2917312"},{"key":"ref79","article-title":"Knowledge distillation thrives on data augmentation","author":"wang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_4"},{"key":"ref75","article-title":"Efficientdet: Scalable and efficient object detection","author":"tan","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01063"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref102","first-page":"arxiv-2104","article-title":"Visual transformer pruning","author":"zhu","year":"2021","journal-title":"ArXiv e-prints"},{"key":"ref76","article-title":"Contrastive representation distillation","author":"tian","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref1","first-page":"953","article-title":"Tkd: Temporal knowledge distillation for active perception","author":"bajestani","year":"0","journal-title":"The IEEE Winter Conference on Applications of Computer Vision"},{"key":"ref71","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"sanh","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref73","article-title":"Addersr: Towards energy efficient image super- resolution","author":"song","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00492-0"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00672"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00682"},{"key":"ref69","article-title":"Layer-wise pruning and auto- tuning of layer-wise learning rates in fine-tuning of deep networks","author":"ro","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378534"},{"key":"ref66","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"},{"key":"ref61","first-page":"116","article-title":"Shufflenet v2: Practical guidelines for efficient cnn architecture design","author":"ma","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191736.pdf?arnumber=10191736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:47:16Z","timestamp":1692640036000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191736\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":102,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191736","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}